Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jerseycheese/agent-skills --skill band-aid-findergit clone --depth 1 https://github.com/jerseycheese/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jerseycheese/agent-skills/band-aid-finder)<a href="https://agentmods.dev/skills/jerseycheese/agent-skills/band-aid-finder"><img src="https://agentmods.dev/badge/skills/jerseycheese/agent-skills/band-aid-finder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jerseycheese/agent-skills/band-aid-finder"><img src="https://agentmods.dev/badge/skills/jerseycheese/agent-skills/band-aid-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.01557 |
| Opus 5.5 | $0.00030 | $0.00623 |
| Sonnet 5.5 | $0.00015 | $0.00311 |
| Haiku 4.5 | $0.00007 | $0.00156 |
Grade A, and why
band-aid-finder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Band-Aid Finder
A band-aid stops the bleeding without treating the wound: the symptom disappears, the defect stays, and it resurfaces later or somewhere else. This skill finds those fixes, traces the symptom back to its cause, and pushes to the fix that actually resolves it — while still allowing a deliberate, documented mitigation when a root-cause fix genuinely isn't the right move right now.
This is the counterweight to kiss. KISS argues against a fix more complex than the problem needs;
this skill argues against a fix so simple it only hides the symptom. The target is the simplest fix
that still reaches the cause — neither the smallest diff nor the largest refactor.
Process
- Identify the symptom and the fix. What visible problem is being addressed, and what does the change actually do?
- Trace to the root cause. Follow the symptom back to why it occurs. Confirm the cause by
reproducing it or reading the code path — don't assert it from a guess. (This is squarely
evidence-checkterritory: "the root cause is X" is an Unverified claim until you've read the path or run the repro this session. Naming a plausible cause is not confirming it.) - Classify the fix against the band-aid signals below.
- Judge: band-aid or real fix? A fix that resolves the traced cause is real, even if small. A fix that leaves the cause in place and only hides its effect is a band-aid.
- Check for a legitimate mitigation. Sometimes suppressing the symptom is the right call for now (see below). If so, it must be documented as deliberate with a follow-up — not left silent.
- Propose the fix — only once the cause is confirmed. If step 2 confirmed the root cause, propose the fix concretely: where the real defect is and the change that resolves it, landing in the right layer rather than patched at the call site. If the cause is not confirmed, do not prescribe a fix — report the evidence gap and the next verification step (the repro to run, the file/path to read) instead. Prescribing a fix for an unconfirmed cause is the exact failure this skill exists to catch.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago Changed · -4 lines · -88 tokens per session a05d07f057eb
- 1mo ago First seen · 119 lines · 162 tokens per session scan A 27af3b5e238f
band-aid-finder is a skill published in the GitHub repository jerseycheese/agent-skills (3 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 1,557 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.
debug-workflow
Run the Maestro debugging workflow for investigation-heavy tasks.
perf-check
Run a Maestro-style performance assessment for hotspots, regressions, and optimization planning.
review-rfc
Review an implemented RFC in a fresh context against its acceptance criteria, RULES.md and the test plan, and save the review to reviews/.
kiss-dry-yagni
Principes KISS, DRY, YAGNI. Use when reviewing code quality or refactoring.
patch-edit
Apply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change suffices.